# Taste Of Pakistan: Agent-Direct Score D (49.2%)

Site: https://tasteofpakistan.de
Report: https://directindex.org/r/tasteofpakistan.de
Scanned: 2026-10-14 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Taste Of Pakistan is hard for agents to use.
An AI assistant can open the website of Taste Of Pakistan. What Taste Of Pakistan offers is in a PDF or an image, which assistants read poorly. To book or order, it is sent to Uber Eats, a marketplace.

## Direct links
- Menu: https://tasteofpakistan.de/assets/docs/menu.pdf

## What to fix first
- **No structured data for the business.** (+15 points) Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations). It is the one block every assistant reads first; the fix kit below has it filled in. Guide: https://directindex.org/guides/structured-data-restaurant
- **Ordering only through ubereats.** (+12 points) Every agent transaction goes through the marketplace and its commission. Add a direct path on your own site, even a simple form. Guide: https://directindex.org/guides/online-ordering-without-delivery-apps
- **Menu or price list is a PDF.** (+3 points) Most agents skip PDFs or read them badly. Publish it as HTML, keep the PDF as a download. Guide: https://directindex.org/guides/menu-pdf-ai
- **No llms.txt.** (no points, still worth doing) Optional today, cheap to add: a short text file describing the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Restaurant",
  "name": "Taste Of Pakistan",
  "url": "https://tasteofpakistan.de",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Münchener Straße 28",
    "postalCode": "60329",
    "addressLocality": "Frankfurt am Main"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 50.1077674,
    "longitude": 8.6690806
  },
  "servesCuisine": [
    "asian"
  ],
  "hasMenu": "https://tasteofpakistan.de/assets/docs/menu.pdf"
}
</script>
```

llms.txt. Save as /llms.txt at the root of the site.

```
# Taste Of Pakistan

> restaurant (asian) in Münchener Straße 28 60329 Frankfurt am Main, Frankfurt.

## Book or order directly

- Menu: https://tasteofpakistan.de/assets/docs/menu.pdf

## About

- Website: https://tasteofpakistan.de
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
```

## Already right
- **robots.txt lets AI crawlers in.** There is no robots.txt, which allows everything.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Uber Eats works with agents through its partners.** Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Read 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en. An assistant that is not a partner may not finish the step there; a direct path on your own domain works for all of them.

## Where it stands
532 of 934 in Frankfurt. Top 57% of the sites scanned in this index.

| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 88% | no |
| Publish the menu or price list as HTML | 73% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 89% | yes |
| Structured data with address, phone and hours | 50% | no |
| Have an llms.txt | 22% | no |

Nearest places with a similar menu: Anjappar Chettinad (B, 144 m, https://directindex.org/r/anjapparfrankfurt.de); Kitakata Ramen Ban Nai (C, 919 m, https://directindex.org/r/bannai-eu.com); The Noodlemaker (F, 1524 m, https://directindex.org/r/the-noodlemaker.de); Tokymon Chay (B, 1940 m, https://directindex.org/r/tokymonchay.de); Asia Express (F, 2210 m, https://directindex.org/r/asiaexpress-ffm.de); Sampan (F, 2331 m, https://directindex.org/r/restaurant-sampan.de); Wok'n Taste Asia (F, 2829 m, https://directindex.org/r/zoo-frankfurt.de); Mai fresh asia Bistro (F, 2855 m, https://directindex.org/r/domainname.de); Bowlwerk FFM (D, 2874 m, https://directindex.org/r/bowlwerk.com); Wen Cheng (B, 2925 m, https://directindex.org/r/wenchengnoodles.com).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.

Against its peers: Sites using Uber Eats 63% (34% A or B, 661 sites); This site 49.2%.

See what an AI agent reads on this site: https://directindex.org/r/tasteofpakistan.de/agent-view

## Businesses like Taste Of Pakistan in Frankfurt

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Frankfurt | 934 | 50% | 23% | 49.2% |
| Sites using Uber Eats in Frankfurt | 6 | 68% | 67% | 49.2% |

The best of the sites using Uber Eats in Frankfurt: Papi (A 90.8%, https://directindex.org/r/originalpapi.de); Burbank (B 76.9%, https://directindex.org/r/burbank-frankfurt.de); Kuli Alma (B 73.8%, https://directindex.org/r/kuli-alma.com); Trattoria Paparazzi (B 73.8%, https://directindex.org/r/paparazzi-ffm.de); Bibis Baguettes & Burgers (D 41.1%, https://directindex.org/r/bibibabu.de).

With the three fixes above (No structured data for the business; Ordering only through ubereats; Menu or price list is a PDF) the score would be about 95.4%: 9th of 934 in Frankfurt, up from 532nd.

## The direct record
What agents get for Taste Of Pakistan, as JSON: https://directindex.org/api/direct/tasteofpakistan.de
- Book: none on record
- Order: none on record
- Menu: https://tasteofpakistan.de/assets/docs/menu.pdf (pdf; from the scan)
- Hours: none on record
- Phone: none on record
- Stable links that count: https://directindex.org/go/tasteofpakistan.de/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- UCP profile (/.well-known/ucp, Google and Shopify's Universal Commerce Protocol): not measured
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): not measured
- MCP server card (/.well-known/mcp/server-card.json): no
- Ordering vendor that takes agent orders (Square, Toast, or a vendor whose terms allow agents): not measured
- Vendor terms for agents, Uber Eats: Through partners. Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Read 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en

Not measured at this scan; the next scan measures it.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 4 | 25 |
| Actionable | 3 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 0 of 5, Not Ready. Cloudflare's report: https://isitagentready.com/tasteofpakistan.de
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: no (how: https://isitagentready.com/.well-known/agent-skills/sitemap/SKILL.md)
- AI bot rules in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/ai-rules/SKILL.md)
- Content Signals in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/content-signals/SKILL.md)
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: no (how: https://isitagentready.com/.well-known/agent-skills/llms-txt/SKILL.md)
- API catalog (RFC 9727): no (how: https://isitagentready.com/.well-known/agent-skills/api-catalog/SKILL.md)
- MCP server card: no (how: https://isitagentready.com/.well-known/agent-skills/mcp-server-card/SKILL.md)
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: no (how: https://isitagentready.com/.well-known/agent-skills/agent-skills/SKILL.md)
- OAuth or OIDC discovery: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-discovery/SKILL.md)
- OAuth protected resource metadata: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-protected-resource/SKILL.md)
- auth.md: no (how: https://isitagentready.com/.well-known/agent-skills/auth-md/SKILL.md)
- Web Bot Auth key directory: no (how: https://isitagentready.com/.well-known/agent-skills/web-bot-auth/SKILL.md)
- ARD capability manifest: no (how: https://isitagentready.com/.well-known/agent-skills/ard/SKILL.md)
- DNS-AID records: no (how: https://isitagentready.com/.well-known/agent-skills/dns-aid/SKILL.md)
- WebMCP tools on the page: no (how: https://isitagentready.com/.well-known/agent-skills/webmcp/SKILL.md)
- JSON-LD for the business: no

Keep watching this business (https://directindex.org/r/tasteofpakistan.de/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/tasteofpakistan.de/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. Reading and scanning stay free; these few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=tasteofpakistan.de&force=1
